Assessment | The gross local assessed value of a property prior to any adjustments for exemptions such as blind, elderly, etc. |
Average Sale Price | The average (mean) sale price among valid sales in the municipality for that year. |
Average Market Value $ | The average (mean) assessed value among valid sales in the municipality for that year. |
Bootstrap
| A computer intensive statistical procedure designed to provide numerous random samples from the original data set that are in turn used to generate the statistics of interest, such as point estimates and confidence intervals. This procedure is particularly helpful when the original set of data is small, in order to give more accurate statistics. |
Broadened Median | The broadened median attempts to preserve the resistance of the median to outliers while also achieving insensitivity to rounding and grouping. |
Coefficient of Concentration | The percentage of observations falling within a specified percentage (i.e. 15%) of a measure of central tendency (median ratio). |
Coefficient of Dispersion [COD] | The COD is a measure of assessment equity and represents the average deviation of a group of ratios from the median ratio expressed as a percentage of the median. A COD is calculated for the entire sampling and for each stratum. |
Coefficient of Variation [COV] | The COV is a measure of relative dispersion of the sample data about the mean of the data. The COV is the standard deviation divided by the mean ratio, expressed as a percentage. |
Confidence Intervals
| For a given confidence level, the range within which one can conclude that a measure of the population (such as the median) lies. |
Confidence Levels | The required degree of confidence in a statistical test or confidence level. A 90% confidence level means that one can be 90% confident that the statistic falls within the indicated range. |
Equalization Ratio
| The DRA will use the weighted mean ratio to equalize the modified assessed value for each municipality. The Assessing Standards Board adopted the use of the weighted mean for equalization only. It has not been adopted or recommended for use for any other purpose. If it can be determined that the weighted mean does not reflect an accurate measure of the municipality’s assessment level, another factor may be used. This is rare and generally occurs when there are insufficient sales in the ratio study. |
Geometric Mean Ratio | The nth root of the product (multiplication) of the ratios, where n is the number of ratios. This is another measure of assessment level, one that is less sensitive than the mean to extreme ratios. |
Harmonic Mean Ratio | Calculated by taking the sum of the reciprocals of each ratio. (The “reciprocal” of a number is the inverse of the number, or 1 divided by the number.) The sum is then divided by the number of ratios, and the reciprocal of that quotient is the harmonic mean. |
Maximum Ratio | The highest ratio for the sales used in the sampling. |
Maximum Sale Price | The highest sales price for the sales used in the sampling. |
Mean Ratio | The average ratio - the sum of ratios divided by the number of ratios. |
Median Absolute Deviation [MAD] | The median of the absolute deviations from the median ratio. The MAD like the COD is a measure of variability. |
Median Ratio | The middle ratio when a set of ratios is arrayed in order of magnitude. |
Minimum Ratio | The lowest ratio for the sales used in the sampling. |
Minimum Sale Price | The lowest sales price for the sales used in the sampling. |
Percentile - 25th & 75th
| The values that divide a set of data into specified percentages when the data are arrayed in ascending order: 25th - the lowest 25% of the ratios 75th - the lowest 75% of the ratios |
Modified Assessed Value | The sum of all local assessed values in the municipality minus the value of property exempted under RSA 72:12-a, 72:37-a and 72:23 IV and 72:36-a. |
Normality Test | A test to determine if the data is considered to be normally distributed or conforms to the bell-shaped curve (Gaussian shape).
Note: Typically, ratio study data does not follow the bell curve. Utilizing the “bootstrap” technique (as defined above) helps to improve the reliability of the measures calculated. |
Price-Related Differential [PRD] | The PRD is calculated by dividing the mean ratio by the weighted mean ratio. It measures vertical inequities (differences in the appraisal of low-value and high-value properties) in assessments. PRDs > 1.03 tend to indicate assessment regressivity (lower-value properties assessed at higher ratios). PRDs < .98 tend to indicate assessment progressivity (lower-value properties assessed at lower ratios than higher-value properties). |
Property Types | The property types are listed as 4-letter abbreviations on the top of each stratified report. For example: resl = residential land; coml = commercial land. For a full listing of property types, refer to property-type listing sent with original municipal assessment sheets. |
Ratio | The ratio for a single sale means the assessment divided by the sale price. |
Sales In Dates & Sales in Strata | The number of sales in dates and number of sales in strata equals the number of sales in the entire sampling or in an individual stratum prior to excluding any sales as invalid. |
Sales Used # and % | The number and percent of sales used for the entire sampling or individual stratum. |
% Sales w/PA-34 | The % of sales used for which an Inventory of Property Transfer, Form PA-34, was received. |
Standard Deviation | The square root of the following quantity: the sum of the squares of the differences between the ratios and their mean, divided by the number of ratios minus one. The standard deviation is a measure of uniformity, but is rarely used in sales ratio data, since much of its interpretation depends on the data having a normal distribution. |
Strata | (stratum, sing.) A class or subset of the population being studied. For example: residential land or waterfront. |
Stratified Analysis | The statistical calculations and report prepared for individual stratum in a municipality. |
Trim Method “Outliers” | A 3.0 trim procedure was used for identifying and removing sales from the sampling as outliers. These sales are identified by a “Yes” in the Trim column of the analysis sheet. |
Total Equalized Valuation | The total equalized value of all property in the municipality as determined in accordance with RSA 21-J:3, XIII. The total equalized valuation includes the equalized valuation of a municipality’s assessed values and the equalized value of payments made in lieu of taxes.
|
Weighted Mean | (a.k.a. aggregate) The sum of the assessments divided by the sum of the sales prices in a ratio study. |